How to Use the Agency Elephant MCP in OpenAI Agents SDK

Q: How do I install the Agency Elephant MCP Server in OpenAI Agents SDK?

Run pip install openai-agents and initialize MCPServerStreamableHttp with your Vinkius endpoint. Pass that directly into the mcpservers list in your Agent constructor. The tools auto-discover immediately.

Q: Can OpenAI Agents SDK trigger Agency Elephant drip campaigns?

Yes. The agent reads available sequences via listcampaigns and launches them using triggerdripcampaign. You can set guardrails in the SDK to require human approval before any emails fire.

Q: Does the Agency Elephant integration with OpenAI Agents SDK support caching?

It does. Set cacheToolsList=True when configuring your server connection. This stops the agent from refetching the tool definitions on every single run, which speeds up execution time.

Connect Agency Elephant to your OpenAI Agents SDK production system to manage insurance leads and trigger drip campaigns automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Agency Elephant MCP to OpenAI Agents SDK

Create your Vinkius account to connect Agency Elephant to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Agency Elephant with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route leads through OpenAI Agents SDK

Your Agency Elephant agent gets insurance prospects into the right buckets fast. Pass the Agency Elephant MCP Server into your agent constructor. It instantly learns how to read your current pipeline using `list_leads` and `list_lead_groups`. When a new prospect hits your system, your agent validates the data and fires off `create_lead`. It then assigns the prospect to specific agent pools by calling `add_lead_to_group`, keeping your commission tracking accurate and your team fed with fresh opportunities.

Automate policy renewal campaigns

Agency Elephant eliminates manual follow-ups that kill conversion rates in the insurance business. Your production agent monitors policy expiration dates and automatically executes `list_campaigns` to find the right retention sequence. Once it identifies the correct sequence, the agent executes `trigger_drip_campaign` for that specific lead. OpenAI's built-in tracing lets you watch exactly when these campaigns launch, so you never have to guess if a renewal email actually went out.

Audit agency performance

Agency Elephant replaces messy CSV exports when tracking who handles which policies. Your agent pulls real-time roster data using `list_workspace_users` and matches it against specific lead assignments via `get_lead_details`. Because you run this through an MCP connection, handoffs between specialized agents happen natively. A reporting agent gathers the raw lead metrics, then passes the context to a management agent that flags underperforming groups.

Setup guide

Set up Agency Elephant MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Agency Elephant tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Agency Elephant tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Agency Elephant tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Agency Elephant Agent",
            instructions="You have access to Agency Elephant tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Agency Elephant. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Agency Elephant now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Agency Elephant MCP in OpenAI Agents SDK

Run `pip install openai-agents` and initialize `MCPServerStreamableHttp` with your Vinkius endpoint. Pass that directly into the `mcp_servers` list in your Agent constructor. The tools auto-discover immediately.

Yes. The agent reads available sequences via `list_campaigns` and launches them using `trigger_drip_campaign`. You can set guardrails in the SDK to require human approval before any emails fire.

It does. Set `cacheToolsList=True` when configuring your server connection. This stops the agent from refetching the tool definitions on every single run, which speeds up execution time.

The tool call fails and returns an error message to the agent. OpenAI's native tracing catches this failure, allowing the agent to either retry with a valid ID from `list_lead_groups` or escalate to a human.

Vinkius runs the server inside a V8 Isolate Sandbox. Your client only accesses the exact prospect names, policies, and agent IDs exposed by the tools, and the ephemeral container destroys itself after the session ends.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript